Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1094 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.0041. Min Range: -4.0041
Max Act: 4.0041. Min Act: -0.1700
Data Index: 1040315 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0041. Min Range: -4.0041
Max Act: 3.9103. Min Act: -0.1700
Data Index: 62381 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0041. Min Range: -4.0041
Max Act: 3.9103. Min Act: -0.1700
Data Index: 534582 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0041. Min Range: -4.0041
Max Act: 3.9103. Min Act: -0.1700
Data Index: 366263 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0041. Min Range: -4.0041
Max Act: 3.8790. Min Act: -0.1700
Data Index: 661716 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0041. Min Range: -4.0041
Max Act: 3.8790. Min Act: -0.1700
Data Index: 843698 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0041. Min Range: -4.0041
Max Act: 3.8478. Min Act: -0.1700
Data Index: 1054190 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0041. Min Range: -4.0041
Max Act: 3.8165. Min Act: -0.1700
Data Index: 377526 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0041. Min Range: -4.0041
Max Act: 3.8478. Min Act: -0.1700
Data Index: 797770 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0041. Min Range: -4.0041
Max Act: 3.8165. Min Act: -0.1700
Data Index: 602350 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0041. Min Range: -4.0041
Max Act: 3.8008. Min Act: -0.1700
Data Index: 1209527 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0041. Min Range: -4.0041
Max Act: 3.8165. Min Act: -0.1700
Data Index: 1189077 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0041. Min Range: -4.0041
Max Act: 3.8008. Min Act: -0.1700
Data Index: 117348 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0041. Min Range: -4.0041
Max Act: 3.8008. Min Act: -0.1700
Data Index: 1039404 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0041. Min Range: -4.0041
Max Act: 3.7695. Min Act: -0.1700
Data Index: 551143 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0041. Min Range: -4.0041
Max Act: 3.7852. Min Act: -0.1700
Data Index: 1351343 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0041. Min Range: -4.0041
Max Act: 3.7852. Min Act: -0.1700
Data Index: 579626 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0041. Min Range: -4.0041
Max Act: 3.7539. Min Act: -0.1700
Data Index: 266234 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0041. Min Range: -4.0041
Max Act: 3.7539. Min Act: -0.1700
Data Index: 705473 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0041. Min Range: -4.0041
Max Act: 3.7539. Min Act: -0.1700
Data Index: 1162056 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19